STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Terra Low vs Step 5 Preview

GPT-6.1 Terra Low leads Step 5 Preview by 2.3 points on StealthMark, 41.3 to 39.0. It leads on 6 of 9 benchmarks, including both games, and Step 5 Preview on 3. GPT-6.1 Terra Low scores higher on Beach, with its largest category advantage in prompt & likeness.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

41.3/100Overall rank 35/55
39.0/100Overall rank 38/55

General Intelligence

34.3/100
37.1/100

Visual Intelligence

53.1/100
41.9/100

Open or local

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6.1 Terra Low
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

  • GPT-6.1 Terra Low
  • Step 5 Preview
  • Other models
  • Median
Context windowTokens per request, max output below
GPT-6.1 Terra Low: Not publishedStep 5 Preview: 1M
SizeTotal and active parameters
GPT-6.1 Terra Low: Not disclosedStep 5 Preview: 600B27B active
Developer
Not publishedStepFun
Input → output
Not publishedText, image, video → text
Architecture
Not publishedSparse mixture-of-experts; 92 layers (88 MoE), 352 routed experts with 8 selected per token plus a shared expert; grouped-query attention with 512-token sliding windows and full attention every fourth layer; 3 multi-token-prediction layers; vision tower for image and video input

Full datasheets, every price and sourceStep 5 Preview ↗

Anticipating threats and planning ahead. Collect coins while avoiding ghosts. Ghosts move before the player each turn, and collisions cost a life. 3 levels in sequence, up to 66 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

GPT-6.1 Terra Low 36.1/100Rank 26/51

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

Step 5 Preview 59.9/100Rank 44/511 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 122 ptsTurn 28 / 28

Points per level

LevelGPT-6.1 Terra LowStep 5 Preview
Level 1Second Thoughts
4 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
8 ptsOut of lives
Pending
Level 3Hide or Flight
9 ptsSurvived
Pending

Cooperative planning and learning from experience. Coordinate two robots to push numbered cores onto matching sockets. Pressure plates hold doors open; moving either robot uses one turn. 5 levels in sequence, up to 152 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

GPT-6.1 Terra Low 62.4/100Rank 23/52

Cleared 4 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Step 5 Preview 40.7/100Rank 30/52

Cleared 4 of 5
Latch: complete playing field
Level 515 ptsTurn 35 / 40

Points per level

LevelGPT-6.1 Terra LowStep 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.2 ptsCleared
9 ptsCleared
Level 3Relay vault
18.8 ptsCleared
18.6 ptsCleared
Level 4Passing bay
10.2 ptsFinished early
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
15 ptsFinished early

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

GPT-6.1 Terra Low

Deformed colored paint and a separate airborne black body establish readable interaction history. Cyan has travelled too far, framing differs substantially, and the mirror system supplies only elementary bands and oval copies. Missing recursive geometry, nested spherical imagery and emitter mapping remain the dominant weaknesses.

Step 5 Preview

The main sphere, airborne black and small colored features occupy broadly appropriate positions. Most of the defining mirror system is absent, and paint interaction remains only partially supported. The small paint features do not visibly establish a separate volume-scale violation.

Score breakdown

CategoryGPT-6.1 Terra LowStep 5 Preview
State at 600 ms22.0/2520.0/25
Camera and placement4.0/1513.5/15
Reflections10.0/12020.0/120
Materials and scale6.0/107.0/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

The judgment

GPT-6.1 Terra Low

Six attached outward-facing heads, delicate scales and soft ivory shading establish an orderly decorative motif. Separate paddle-shaped bodies replace the required interlocking loops and leave no enclosed central hexagon. Surface detail provides interest, but repeated simple forms, schematic faces and limited anatomical modeling constrain the result.

Step 5 Preview

A charming diagonal climber and warm palette communicate the central idea. Simple rounded construction, crowded limb counting, uncertain footholds and an unattached upper shelf limit its physical coherence. Growth bands and the yarn trail add specificity, but the requested material distinctions and unravelled bootie remain underdeveloped.

Score breakdown

CategoryGPT-6.1 Terra LowStep 5 Preview
Task & likeness4.0/106.0/10
Anatomy & construction3.5/104.5/10
Space & placement4.5/105.0/10
Light & reflections5.5/105.5/10
Purposeful detail5.5/105.5/10
Artistry & character5.0/105.0/10
Materials & effects5.5/106.0/10
Visual integrity4.0/105.0/10

Benchmark task

GPT-6.1 Terra Low

A pale serpent woven into an interlocking knot tests connected anatomy, repeated structure and readable overlaps. Organic surface detail must work with the overall geometry.

Step 5 Preview

Character scenes test expression, anatomy, materials and coherent visual construction.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

GPT-6.1 Terra Low

A recognizable, coherent portrait with purposeful facial detail, warm local volume and layered scenery. The frontal pose, enlarged face, merged hands and shallow clothing construction substantially limit replication and drawing skill. The visible successes support retaining the current assessment.

Step 5 Preview

A recognizable, coherent simplification with purposeful facial contours and differentiated fingers. These provide more construction and detail than the broad silhouette alone suggests. The oversized face, frontal seated pose, unresolved wrists and sparse landscape still substantially limit likeness, depth and finish.

Score breakdown

CategoryGPT-6.1 Terra LowStep 5 Preview
Task & likeness5.0/104.0/10
Anatomy & construction4.5/104.0/10
Space & placement5.0/104.0/10
Light & reflections6.0/103.5/10
Purposeful detail5.0/104.0/10
Artistry & character5.5/104.0/10
Materials & effects5.0/103.0/10
Visual integrity6.0/103.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Same task instructions

Creativity, perspective and visual beauty.

The judgment

GPT-6.1 Terra Low

A coherent sunset scene demonstrates the beach, animals, birds and reflections. Flowing silhouettes, warm color transitions and intact attachments are its strongest properties. Simplified anatomy, the turtle's elevated viewing angle and symbolic surface effects constrain drawing complexity and physical depth.

Step 5 Preview

A recognizable sunset beach with clear warm-cool contrast and playful accessories. Basic animal construction, shallow foreground placement and schematic reflections limit spatial and physical credibility. Sparse descriptive detail and abruptly ended sky bands constrain the finish.

Score breakdown

CategoryGPT-6.1 Terra LowStep 5 Preview
Task & likeness8.0/104.0/10
Anatomy & construction5.5/103.0/10
Space & placement5.5/103.5/10
Light & reflections6.5/103.5/10
Purposeful detail6.0/103.0/10
Artistry & character5.0/103.0/10
Materials & effects5.5/103.5/10
Visual integrity7.5/104.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Same task instructions

Physical reasoning, light and visual reconstruction.

The judgment

GPT-6.1 Terra Low

This benchmark has not been assessed yet.

Step 5 Preview

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Same task instructions

Scene composition and interacting subjects.

The judgment

GPT-6.1 Terra Low

Recognizable animals, a coherent craft and sweeping wake make an appealing cartoon. Basic limb construction, weakly demonstrated raccoon seating and limited shared perspective constrain the scene. Small identifying details work well, while lighting and materials remain broadly graphic.

Step 5 Preview

Recognizable animals, a bright palette and identifying accessories support a basic cartoon. Primitive anatomy, partial seated support, unresolved steering and weak hull-water contact limit the central action. Lighting and spray provide atmosphere without establishing convincing physical depth.

Score breakdown

CategoryGPT-6.1 Terra LowStep 5 Preview
Task & likeness6.5/104.0/10
Anatomy & construction5.0/104.5/10
Space & placement5.5/103.0/10
Light & reflections4.5/103.5/10
Purposeful detail6.0/104.0/10
Artistry & character5.0/103.5/10
Materials & effects5.0/103.0/10
Visual integrity6.0/103.0/10

Benchmark task

A jet-ski scene pairs a canine driver with a raccoon passenger. It tests the placement and contact of interacting subjects, along with vehicle construction.

Pelican

Same task instructions

Subject construction and spatial relationships.

The judgment

GPT-6.1 Terra Low

A coherent coastal illustration with a distinctive pelican, controlled contours and clearly organised bicycle wheels. Visible saddle support and shaped neck and wing contours earn credit beyond basic geometric construction. Rubbery legs, unresolved pedal contacts and absent steering contact limit the riding action. Lighting and materials remain restrained and spatially shallow.

Step 5 Preview

The pelican and bicycle are recognizable, with a pleasant palette and basic diffuse shading. The riding relationship fails physically: the bird is unsupported, the front wheel is unmounted, and pedalling is unresolved. Simple geometric construction and sparse material treatment further limit the drawing.

Score breakdown

CategoryGPT-6.1 Terra LowStep 5 Preview
Task & likeness7.0/103.0/10
Anatomy & construction5.5/103.0/10
Space & placement6.0/103.0/10
Light & reflections5.5/103.0/10
Purposeful detail6.5/104.0/10
Artistry & character6.0/103.0/10
Materials & effects6.0/103.0/10
Visual integrity6.0/102.0/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.